MIT Laboratory for Information and Decision Systems (Sunbochen Tang, Navid Azizan, Themistoklis Sapsis) · Physics-constrained Chaos Models

Physically consistent AI models of chaotic systems

Researchers at MIT LIDS present a method that enforces energy dissipation as a hard constraint on machine learning models of chaotic systems. The model learns an energy-like function and a confining boundary, and a projection layer keeps predictions bounded over arbitrarily long forecasts. The team reports that the approach closely matched true outcomes on several physical systems, where conventional models drifted into impossible predictions. The paper is published in PNAS, and the team says it is making the information freely available.

Open the source ↗

Similar Research & Safety releases

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.